Electronic apparatus and controlling method thereof

Abstract

An electronic apparatus may include a memory that stores first information regarding a plurality of first artificial intelligence models trained to perform image processing differently from each other and second information regarding a second artificial intelligence model trained to identify a type of an image by predicting a processing result of the image by each of the plurality of first artificial intelligence models. The electronic apparatus may further include a processor configured to identify a type of an input image by inputting the input image to the second artificial intelligence model stored in the memory, and process the input image by inputting the input image to one of the plurality of first intelligence models stored in the memory based on the identified type.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS[0001]This application is a continuation of U.S. patent application Ser. No. 17 / 081,510, filed on Oct. 27, 2020, which claims priority from Korean Patent Application No. 10-2019-0150746, filed in the Korean Intellectual Property Office on Nov. 21, 2019, the disclosure of which is incorporated herein by reference.BACKGROUND1. Field[0002]Aspects of exemplary embodiments of the present disclosure relate to an electronic apparatus and a controlling method thereof and more particularly, to an electronic apparatus that processes an input image using an artificial intelligence model and a controlling method thereof.2. Description of the Related Art[0003]Recently, an electronic apparatus may perform image processing using a neural network technology which is represented by deep learning that has been developed rapidly. For example, the neural network technology may be applied to segmentation, super-resolution, HDR, etc.[0004]Such a neural network techn...

AI Technical Summary

Benefits of technology

[0010]The present disclosure is provided in accordance with the above-described needs, and aims at providing an electronic apparatus for improving the processing performance of an input image by changing a processing method according to the type of the input image and controlling method thereof.

[0028]According to the various embodiments of the present disclosure, the electronic apparatus may identify the type of an input image using an artificial intelligence model, and improve processing performance of the input image by processing the input image using another artificial intelligence model corresponding to the identified type.

Problems solved by technology

However, because of a limited computing resource, neural network algorithms may be optimized, but they do not reflect all the characteristics of inputs.

Specifically, if a single neural network model is applied to all inputs, desired results may not be produced for all inputs.

However, as illustrated in FIG. 1C, various side effects (e.g., jagging or blurring) may be generated in an image with text.

Due to such side effects, applying the same neural network model to all inputs is a problem in neural network technology.

However, in the former “sensing” case, the side effects of an image (e.g., after upscaling) should be sensed and eliminated, but the method is not appropriate in an environment where computing resources are limited.

In the latter “storing” case, there is a problem that there is no way of processing when there is no information in the input image.

Images